Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
git clone --depth 1 https://github.com/FlorianBruniaux/claude-code-pluginsWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/florianbruniaux/claude-code-plugins/routines-discover)<a href="https://agentmods.dev/commands/florianbruniaux/claude-code-plugins/routines-discover"><img src="https://agentmods.dev/badge/commands/florianbruniaux/claude-code-plugins/routines-discover/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/commands/florianbruniaux/claude-code-plugins/routines-discover"><img src="https://agentmods.dev/badge/commands/florianbruniaux/claude-code-plugins/routines-discover.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00039 | $0.00952 |
| Opus 5.5 | $0.00016 | $0.00381 |
| Sonnet 5.5 | $0.00008 | $0.00190 |
| Haiku 4.5 | $0.00004 | $0.00095 |
Grade B, and why
routines-discover scanned grade B with 1 finding against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Reads agent configuration directoriesmediumAgent snooping
.claude/, .codex/, .gemini/ hold keys, settings and other credentials a mod has no legitimate need for.
- Any monitoring, deploy, or ops configuration you find If MCP connectors are configured in `.claude/settings.json`, note which external services are connected. How it starts
The opening of the file, as written. The whole thing — 105 lines — stays where its author put it; the contents beside it link to each section on GitHub.
Routines Use Case Discovery
Analyzes this codebase and surfaces actionable Routine candidates across the three trigger types.
Usage: /routines-discover — no arguments needed. Run it in the root of any project.
What Are Routines
A Routine is an autonomous Claude Code session running on Anthropic-managed cloud infrastructure, triggered in three ways:
| Trigger | How it fires |
|---|---|
| Schedule | Recurring cron cadence (min 1 hour) |
| API | HTTP POST to a per-routine endpoint with bearer token |
| GitHub events | Repository events: PR opened/merged, push, issue, workflow run, etc. |
Each run clones a fresh copy of the GitHub repository, runs a full Claude Code session with configured MCP connectors (Slack, Linear, GitHub, Google Drive…), and can create branches, open PRs, post messages, and call external APIs. No local machine required.
Daily limits: Pro 5/day · Max 15/day · Team/Enterprise 25/day.
Instructions
Step 1 — Read the codebase
Before generating any output, silently read:
README.mdorCLAUDE.mdto understand the project purpose and stackpackage.json,Cargo.toml,pyproject.toml, or equivalent for dependencies.github/workflows/to understand existing CI/CD automation- Any monitoring, deploy, or ops configuration you find
If MCP connectors are configured in .claude/settings.json, note which external services are connected.
Step 2 — Analyze against five dimensions
For each dimension, think concretely about this specific project before writing anything.
1. Scheduled maintenance What recurring work currently requires a human to run manually or remember to do? Think: dependency audits, stale issue/PR triage, test flakiness reports, coverage drift, TODO comment tracking, dead code detection, daily or weekly summaries.
2. Event-driven reactions What should happen automatically when a PR is opened, merged, or closed — but doesn't today because no one gets to it? Think: review checklists, changelog updates, cross-repo sync, Slack notifications with context, label enforcement, docs updates on API changes.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 1mo ago First seen · 105 lines · 39 tokens per session scan B 1c032a9ce601
routines-discover is a command published in the GitHub repository FlorianBruniaux/claude-code-plugins (42 stars, last pushed 1mo ago), licensed MIT. It adds 39 tokens to every session and 952 once invoked, about $0.0002 per session on Opus 5.5. A static security scan graded it B with 1 finding (reads agent configuration directories). No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-04.
Other commands, from other repositories
team
Virtual eng team orchestrator. Runs a goal end-to-end through the whole team — strategy → plan → build → QA → ship — conducted by the engineering-manager, delegating to every specialist. One entry point that connects /ceo-review, /eng-review, /qa, and /ship.
content-start
Content production session start command. Gives the daily content session a structured start, shows pending work, and sets priorities.
proposal
Client proposal command. Builds a professional client proposal from project summaries. Valid for 30 days.
dashboard
Daily statistics panel. Presents task, audit, event, and performance data as a unified table.
onboard
Project onboarding command. For adapting to a new project quickly and thoroughly.
start
Badi session start command. Runs new-project onboarding or a daily kickoff.